© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16112
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Normdatei
    -0.59
     незавершена
    -0.58
    تقاوى
    -0.57
     defaultstate
    -0.57
    ChildScrollView
    -0.57
    +#+
    -0.55
     мәкал
    -0.54
    basicConfig
    -0.54
    OGND
    -0.54
     发表于
    -0.53
    POSITIVE LOGITS
    mybatisplus
    0.62
     the
    0.56
    ObjectMeta
    0.56
    med
    0.53
     irré
    0.52
     officinalis
    0.51
     agents
    0.51
    wat
    0.50
    atum
    0.50
     Sécurité
    0.49
    Activations Density 0.019%

    No Known Activations